# ECSIC: Epipolar Cross Attention for Stereo Image Compression

arXiv: https://arxiv.org/abs/2307.10284 · HTML: https://mlsanity.com/paper/2307.10284/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 18 Jul 2023.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Entroformer: A Transformer-based Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2202.05492/) (2022)
- [Enhanced Invertible Encoding for Learned Image Compression](https://mlsanity.com/paper/2108.03690/) (2021)
- [Lossy Compression with Gaussian Diffusion](https://mlsanity.com/paper/2206.08889/) (2022)
- [Improving Inference for Neural Image Compression](https://mlsanity.com/paper/2006.04240/) (2020)
- [Causal Contextual Prediction for Learned Image Compression](https://mlsanity.com/paper/2011.09704/) (2020)
- [Deep Generative Models for Distribution-Preserving Lossy Compression](https://mlsanity.com/paper/1805.11057/) (2018)
- [Joint Global and Local Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/2112.04487/) (2021)
- [Soft then Hard: Rethinking the Quantization in Neural Image Compression](https://mlsanity.com/paper/2104.05168/) (2021)
- [Learning Accurate Entropy Model with Global Reference for Image Compression](https://mlsanity.com/paper/2010.08321/) (2020)
- [Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression](https://mlsanity.com/paper/2203.02452/) (2022)
- [PO-ELIC: Perception-Oriented Efficient Learned Image Coding](https://mlsanity.com/paper/2205.14501/) (2022)
- [DSIC: Deep Stereo Image Compression](https://mlsanity.com/paper/1908.03631/) (2019)
- [Neural Distributed Image Compression with Cross-Attention Feature Alignment](https://mlsanity.com/paper/2207.08489/) (2022)

## Built on by (most cited first, 8 of 8)

- [Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model](https://mlsanity.com/paper/2407.10632/) (2024)
- [FCNR: Fast Compressive Neural Representation of Visualization Images](https://mlsanity.com/paper/2407.16369/) (2024)
- [CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression](https://mlsanity.com/paper/2403.08505/) (2024)
- [Neural Stereo Video Compression with Hybrid Disparity Compensation](https://mlsanity.com/paper/2504.20383/) (2025)
- [Synthesizing Consistent Novel Views via 3D Epipolar Attention without Re-Training](https://mlsanity.com/paper/2502.18219/) (2025)
- [Accelerating Learned Image Compression Through Modeling Neural Training Dynamics](https://mlsanity.com/paper/2505.18107/) (2025)
- [Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates](https://mlsanity.com/paper/2605.22061/) (2026)
- [Echo4DIR: 4D Implicit Heart Reconstruction from 2D Echocardiography Videos](https://mlsanity.com/paper/2605.22066/) (2026)

## Abstract (arXiv)

In this paper, we present ECSIC, a novel learned method for stereo image compression. Our proposed method compresses the left and right images in a joint manner by exploiting the mutual information between the images of the stereo image pair using a novel stereo cross attention (SCA) module and two stereo context modules. The SCA module performs cross-attention restricted to the corresponding epipolar lines of the two images and processes them in parallel. The stereo context modules improve the entropy estimation of the second encoded image by using the first image as a context. We conduct an extensive ablation study demonstrating the effectiveness of the proposed modules and a comprehensive quantitative and qualitative comparison with existing methods. ECSIC achieves state-of-the-art performance in stereo image compression on the two popular stereo image datasets Cityscapes and InStereo2k while allowing for fast encoding and decoding.